rocprofv3: summary reports + more JSON metadata (#1029)

* Move include/rocprofiler-sdk/cxx/details/delimit.hpp to tokenize.hpp

* Update docs/how-to/using-rocprofv3.rst

- fix code block indents
- reorder rocprofv3 options, limit them to important options
- add docs for `--runtime-trace`

* Update rocprofv3.py

- parser argument groups
- new `--runtime-trace` option
- new `--summary` option
- new `--summary-per-domain` option
- new `--summary-groups` option
- new `--summary-output-file` option
- new `--summary-units` option

* Update lib/rocprofiler-sdk/hsa/async_copy.cpp

- fix async copy operation names: add "MEMORY_COPY_" prefix

* lib/rocprofiler-sdk-tool: update statistics.{hpp,cpp}

- statistics<>::get_percent function
- stats_entry_t struct
- stats_formatter struct
- percentage struct
- std::to_string(::rocprofiler::tool::percentage)

* lib/rocprofiler-sdk-tool: update domain_type.{hpp,cpp}

- reorder domain_type enum values

* lib/rocprofiler-sdk-tool: update generateCSV.{hpp,cpp}

- separate writing CSV from accumulating statistics
- a lot of functionality was moved to statistics.{hpp,cpp}

* lib/rocprofiler-sdk-tool: update output_file.{hpp,cpp}

- output_stream_t struct
- get_output_stream(...) returns output_stream_t instance

* lib/rocprofiler-sdk-tool: update generateJSON.cpp

- update get_output_stream usage to output_stream_t

* lib/rocprofiler-sdk-tool: update generateOTF2.cpp

- header include order tweak

* lib/rocprofiler-sdk-tool: update buffered_output.hpp

- stats_data_t was renamed to stats_entry_t

* lib/rocprofiler-sdk-tool: update generatePerfetto.cpp

- header include tweak

* lib/rocprofiler-sdk-tool: update tmp_file_buffer.hpp

- emit warning message if write_ring_buffer fails after offloading instead of aborting
- prefer placement new instead of assignment in write_ring_buffer

* lib/rocprofiler-sdk-tool: add generateStats.{hpp,cpp}

- functions for accumulating statistics

* Update tests/rocprofv3/tracing-hip-in-libraries/CMakeLists.txt

- accommodate tweak to CSV output file name for HIP and HSA traces

* lib/rocprofiler-sdk-tool: update config.{hpp,cpp}

- new config variables
  - stats_summary
  - stats_summary_per_domain
  - summary_output
  - stats_summary_unit_value
  - stats_summary_unit
  - stats_summary_file
  - stats_summary_groups
- support output keys for hostname: %hostname% / %h

* lib/rocprofiler-sdk-tool: update tool.cpp

- support summary output

* Documentation fixes

* Test for summary output

* Update tests/bin/transpose to use more ROCTx

- also support building with the roctracer ROCTx

* Remove roctxMark from OTF2 + fix kernel-rename tests

- following more ROCTx calls in transpose, kernel-rename validation had to be updated

* JSON metadata + JSON summary

- add serialization support for config
- add serialization support for statistics
- additions to json spec
  - rocprofiler-sdk-tool/metadata/config
  - rocprofiler-sdk-tool/metadata/command
  - rocprofiler-sdk-tool/summary
- config output_keys support for NVIDIA %q{<ENV-VAR>} syntax
- config output_keys support keys within keys

* rocprofv3 --summary-groups warning if no domain matches

- emit warning if a regex in for summary groups did not match any domain names

* Compile fix for lib/rocprofiler-sdk-tool/tool.cpp

- get_config().scratch_memory_trace
- pass contributions to write_json

* Update rocprofv3.py to preload rocprofiler-sdk-roctx

- appended to LD_PRELOAD when args.marker_trace is enabled

* Fix ReST link errors about subtitle underline being too short

* Patch tokenization of config::stats_summary_groups

- guard against array values of empty strings

* Tweak rocprofv3 summary test

- input-summary.yaml (used by rocprofv3-test-summary-inp-yaml-execute) only provides one summary group regex

* Disable LD_PRELOAD of librocprofiler-sdk-roctx.so

- this causes problems in the sanitizers, will be addressed in another PR

[ROCm/rocprofiler-sdk commit: 395f01b689]

projects/rocprofiler-sdk/source/lib/rocprofiler-sdk-tool/tool.cpp

@@ -28,8 +28,10 @@
 #include "generateJSON.hpp"
 #include "generateOTF2.hpp"
 #include "generatePerfetto.hpp"
+#include "generateStats.hpp"
 #include "helper.hpp"
 #include "output_file.hpp"
+#include "statistics.hpp"
 #include "tmp_file.hpp"
 
 #include "lib/common/environment.hpp"
@@ -1335,7 +1337,7 @@ tool_init(rocprofiler_client_finalize_t fini_func, void* tool_data)
             "buffer tracing service for memory copy configure");
     }
 
-    if(tool::get_config().scratch_memory)
+    if(tool::get_config().scratch_memory_trace)
     {
         ROCPROFILER_CALL(rocprofiler_create_buffer(get_client_ctx(),
                                                    buffer_size,
@@ -1500,21 +1502,32 @@ api_registration_callback(rocprofiler_intercept_table_t,
                      "Iterate rocporfiler agents")
 }
 
-using stats_data_t = ::rocprofiler::tool::stats_data_t;
+using stats_data_t       = ::rocprofiler::tool::stats_data_t;
+using stats_entry_t      = ::rocprofiler::tool::stats_entry_t;
+using domain_stats_vec_t = ::rocprofiler::tool::domain_stats_vec_t;
 
 template <typename Tp, domain_type DomainT>
 void
 generate_output(rocprofiler::tool::buffered_output<Tp, DomainT>& output_v,
-                std::unordered_map<domain_type, stats_data_t>&   contributions_v)
+                domain_stats_vec_t&                              contributions_v)
 {
     if(!output_v) return;
 
     output_v.read();
 
+    if(tool::get_config().stats || tool::get_config().summary_output)
+    {
+        output_v.stats = rocprofiler::tool::generate_stats(tool_functions, output_v.element_data);
+    }
+
+    if(output_v.stats)
+    {
+        contributions_v.emplace_back(output_v.buffer_type_v, output_v.stats);
+    }
+
     if(tool::get_config().csv_output)
     {
-        output_v.stats = rocprofiler::tool::generate_csv(tool_functions, output_v.element_data);
-        contributions_v.emplace(output_v.buffer_type_v, output_v.stats);
+        rocprofiler::tool::generate_csv(tool_functions, output_v.element_data, output_v.stats);
     }
 }
 
@@ -1543,7 +1556,7 @@ tool_fini(void* /*tool_data*/)
     auto counters_output =
         counter_collection_buffered_output_t{tool::get_config().counter_collection};
     auto scratch_memory_output =
-        scratch_memory_buffered_output_t{tool::get_config().scratch_memory};
+        scratch_memory_buffered_output_t{tool::get_config().scratch_memory_trace};
 
     auto node_id_sort = [](const auto& lhs, const auto& rhs) { return lhs.node_id < rhs.node_id; };
 
@@ -1561,7 +1574,7 @@ tool_fini(void* /*tool_data*/)
         rocprofiler::tool::generate_csv(tool_functions, _agents);
     }
 
-    auto contributions = std::unordered_map<domain_type, stats_data_t>{};
+    auto contributions = domain_stats_vec_t{};
 
     generate_output(kernel_dispatch_output, contributions);
     generate_output(hsa_output, contributions);
@@ -1580,6 +1593,7 @@ tool_fini(void* /*tool_data*/)
     {
         rocprofiler::tool::write_json(tool_functions,
                                       getpid(),
+                                      contributions,
                                       _agents,
                                       _counters,
                                       &hip_output.element_data,
@@ -1617,6 +1631,11 @@ tool_fini(void* /*tool_data*/)
                                       &scratch_memory_output.element_data);
     }
 
+    if(tool::get_config().summary_output)
+    {
+        rocprofiler::tool::generate_stats(tool_functions, contributions);
+    }
+
     auto destroy_output = [](auto& _buffered_output_v) { _buffered_output_v.destroy(); };
 
     destroy_output(kernel_dispatch_output);